CENG 566 - PROJECT PAGE

Project Title: A Learning Based Method for Super-Resolution of Low Resolution Images

Abstract : The main objective of this project is the study of a learning based method for super-resolving low resolution images. The domain specific prior is incorporated into super resolution by the means of learning based estimation of missing details. Images are decomposed into fixed size patches in order to deal with time and space complexity. The problem is modeled by Markov Random Field which enforces resulting images to be spatially consistent. The spatial interactions are coupled with a similarity constraint which should be established between high-resolution training image patches and low resolution observations.

    • Project Report in html1, pdf, and ps formats

    • Presentation in pdf format

    • Source code in pdf and tgz formats. (Use make command to compile the program)

    • Training (15 MB) and Test (8 MB) databases. The images are in pnm format. Training and test images are in 192x304 and 12x19 resolution respectively.

Original Image
 Low resolution
 Estimated without
spacial interaction
 Estimated with
spacial interaction

The figures are not placed well into the html document due to the bugs in latex2html command.

1